Errors, Type I and Type II
Published Online: 30 JAN 2010
Copyright © 2010 John Wiley & Sons, Inc. All rights reserved.
Corsini Encyclopedia of Psychology
How to Cite
Hancock, G. R. 2010. Errors, Type I and Type II. Corsini Encyclopedia of Psychology. 1–2.
- Published Online: 30 JAN 2010
The goal of most social science research is to infer whether variables relate to each other in one or more populations of interest. Statistical tests are a tool used to assist in this inferential process by evaluating data from samples drawn from the population(s) of interest; these statistical tests are, however, by no means foolproof. Occasionally sample information would seem to imply that, for example, variable X is related to variable Y in the population, when in fact no such population relation exists. Such an inaccurate inference is termed a Type I Error (or “alpha error”). On the other hand, sample data may seem to imply that X and Y appear unrelated, when indeed those variables do have a relation in the population. This inaccurate inference is termed a Type II Error (or “beta error”). These two types of errors are discussed in the context of an illustrative research example.